Maintenance Matters Focus on: Maintenance 4.0 12 | Plant & Works Engineering www.pwemag.co.uk June/July 2024 New horizons in a world of AI and Big Data Miron Shtiglitz, VP for Product and Delivery at quality inspection specialist QualiSense, forecasts a future where data from inspection not only underpins maintenance schedules, but informs the very design of the product itself. The key difference between preventive maintenance and predictive maintenance is that the latter means completing maintenance only when needed, as opposed to scheduled intervals. With Industry 4.0, manufacturing data will allow us to gradually replace preventive maintenance with predictive maintenance, but can we go further than this? Anyone familiar with Industry 4.0 has likely encountered the concept of predictive maintenance. By harnessing the data from machine sensors, we can more accurately predict when maintenance activity is actually required, rather than preserving with the fixed schedules typical of preventive maintenance. Optimising maintenance schedules this way means reduced labour and material costs, or so the theory goes. Many companies are making great strides in this field and we are more accurately predicting machine health. In my home country of Israel, Augury is a good example of a company working in this area. You build a sensor that is attached to a machine, it collects data on parameters like sound and vibration and uses this data to predict when you need to carry out maintenance. We have also seen some companies try to do this with cars. By listening to the noises the car makes, you can potentially determine what fault is likely to occur and take preventive action before it is too late. Level two and three The data gathered from inspection systems could form an additional layer to this approach. With AI, the data gathered from these intelligent inspection systems could be correlated with data from predictive maintenance technologies. For example, we might find correlations between the quality of a product and the last time scheduled maintenance activity was performed. In order to make this approach viable, you need very large volumes of data. However, as we enter the era of Big Data, this additional layer opens new possibilities. Looking slightly further ahead, the data gathered from quality inspection systems and the software that supports them will not only enhance the power of predictive maintenance, it will shape the design of the product itself. By using data to make the correct decisions during the design phase, we can reduce the risk of defects further along. Imagine, for example, you are able to analyse correlations between the 3D structure
RkJQdWJsaXNoZXIy MjQ0NzM=